[论文解读] Multi-task Learning Approach for Modulation and Wireless Signal Classification for 5G and Beyond: Edge Deployment via Model Compression
本文提出了一种轻量级多任务学习(MTL)框架,可联合分类调制格式与无线信号类型(如雷达和通信波形),适用于6G及以后网络,通过模型压缩实现在边缘设备上的高效部署。该MTL模型在10 dB信噪比下实现99.2%的信号分类准确率和98.9%的调制分类准确率,经过INT8量化后模型尺寸缩小至251.6 kB(减少11.8倍),在资源受限的边缘设备上展现出高精度与高效率。
Future communication networks must address the scarce spectrum to accommodate extensive growth of heterogeneous wireless devices. Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, secure communications, among others. Consequently, comprehensive spectrum awareness on the edge has the potential to serve as a key enabler for the emerging beyond 5G networks. State-of-the-art studies in this domain have (i) only focused on a single task - modulation or signal (protocol) classification - which in many cases is insufficient information for a system to act on, (ii) consider either radar or communication waveforms (homogeneous waveform category), and (iii) does not address edge deployment during neural network design phase. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks based multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks while considering heterogeneous wireless signals such as radar and communication waveforms in the electromagnetic spectrum. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. We additionally include experimental evaluations of the model with over-the-air collected samples and demonstrate first-hand insight on model compression along with deep learning pipeline for deployment on resource-constrained edge devices. We demonstrate significant computational, memory, and accuracy improvement of the proposed model over two reference architectures. In addition to modeling a lightweight MTL model suitable for resource-constrained embedded radio platforms, we provide a comprehensive heterogeneous wireless signals dataset for public use.
研究动机与目标
- 为密集、异构的无线环境中的综合频谱感知需求提供解决方案,这些环境中共存雷达与通信信号。
- 克服现有单任务模型仅关注调制或协议分类的局限性,这些模型通常局限于同质信号域。
- 设计一种深度学习模型,兼具高精度与在资源受限边缘设备上的可部署性,并从一开始就集成模型压缩技术。
- 通过多任务学习联合学习调制与信号分类任务,以提升泛化能力与效率。
- 公开发布一个通过空中测量获取的异构无线信号数据集(RadComOta),以支持未来研究。
提出的方法
- 设计一种轻量级MTL神经网络架构,使调制与信号分类分支共享早期卷积特征。
- 使用包含多样化雷达与通信波形的合成数据集和空中测量(OTA)数据集对模型进行训练。
- 利用TensorFlow Lite的量化感知训练(QAT)将FP32模型转换为INT8量化模型,以实现边缘设备部署。
- 通过在验证集上进行校准,采用训练后量化方法,最小化压缩过程中的精度损失。
- 使用TensorFlow Lite的默认优化策略对模型进行优化,实现8位权重精度,降低模型尺寸。
- 在Intel Core i5-3230M CPU上评估推理性能,指标包括FLOPs、参数量、内存占用和延迟。
实验结果
研究问题
- RQ1多任务学习框架是否能在异构频谱环境中,同时提升调制格式与无线信号类型分类的精度与效率?
- RQ2通过INT8量化实现的模型压缩对边缘设备上的分类精度与部署可行性有何影响?
- RQ3与VTCNN和DRCNN等现有架构相比,所提出的MTL模型在计算与内存开销方面降低了多少?
- RQ4在真实空中传播条件下,该模型能否在多种信号类型(雷达与通信)下保持高精度?
- RQ5共享表征学习对泛化能力与可扩展性有何影响,特别是在扩展至其他信号表征任务(如发射源分类、带宽回归、采样率估计)时?
主要发现
- 与VTCNN和DRCNN的MTL版本相比,所提MTL模型分别将FLOPs降低91.06%,参数量减少约75%。
- 在10 dB信噪比下,模型实现98.9%的调制分类准确率与99.2%的信号分类准确率,在0 dB及以上信噪比下准确率均超过98%。
- INT8量化将模型尺寸从2.97 MB(FP32)压缩至251.6 kB,实现11.8倍的压缩率,且精度损失可忽略不计。
- 在Intel Core i5-3230M CPU上,推理延迟为8.4 ms,内存占用分别较VTCNN-MTL和DRCNN-MTL降低90.5%与73.8%。
- 模型展现出强大的泛化能力与可扩展性,可轻松扩展至发射源分类、带宽回归与采样率估计等未来任务。
- 公开发布了包含空中测量获取的雷达与通信信号的RadComOta数据集,以支持未来无线信号识别研究。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。